© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5257
    Prev
    Next
    INDEX
    Explanations

    elements related to dates, events, or releases in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.76
    \{\\
    -0.73
     ModelExpression
    -0.72
    NameInMap
    -0.71
    AndEndTag
    -0.69
     surla
    -0.63
     HasFactory
    -0.60
    intios
    -0.57
    GTCX
    -0.57
    opsida
    -0.57
    POSITIVE LOGITS
     Bis
    0.45
     Nare
    0.41
    Bis
    0.41
     par
    0.40
     Sally
    0.40
     s
    0.39
     BOB
    0.39
    setCustom
    0.38
     tot
    0.38
     Dil
    0.38
    Activations Density 4.346%

    No Known Activations